example 01
Finding the best prompt wording
A team wants to know which of three system-prompt versions produces the best summaries, judged by the same scoring rules every time.
you, to your agent
"Use the improve-fast skill to test three summarization prompts: concise, detailed, and bulleted. Score each summary 0–1 like this: 1.0 if it needs no edits, 0.5 if it needs small edits, 0.0 if it needs a rewrite. Let me know when there's a winner."
your agent
Tries a version, generates a summary with it, scores that summary against the rules (or has you confirm the score), and repeats — sending more tries to whichever version is doing best while still checking the others. After about 60 scored tries, it's confident enough to report: detailed wins, averaging 0.81 across 21 tries versus 0.68 and 0.61 for the other two, and updates the production prompt.